A single click mounted a covert, multistage attack against Copilot
NegativeTechnology
- A recent exploit has demonstrated a covert, multistage attack against Microsoft's Copilot, successfully exfiltrating user data from chat histories even after chat windows were closed. This incident raises significant concerns about the security vulnerabilities associated with AI-driven applications.
- The attack's implications are particularly troubling for Microsoft, as it undermines user trust in Copilot's security measures and highlights the ongoing challenges the company faces in safeguarding its AI technologies against sophisticated threats.
- This incident reflects a broader trend of increasing scrutiny and skepticism towards AI technologies, particularly as users express concerns over data privacy and security. The backlash against AI tools, coupled with recent announcements regarding the removal of competing chatbots from platforms like WhatsApp, underscores the contentious landscape in which these technologies operate.
— via World Pulse Now AI Editorial System